semster

1. HICET – Department of Artificial Intelligence and Machine Learning
Programme Course Code Name of the Course L T P C
B. Tech 19AI6201 Theory of Computation 3 0 0 3
Course
Objective
1. To understand the basic concepts of automata theory and finite automaton
2. To extend the concepts of automata theory in regular languages and expressions
3. To learn about context free grammars and the normalizations of CFG
4. To acquire the importance of push down automata with representations and various
models of turing machines with its applications
5. To discover the facts in decidability and tractability and to study the complexity classes
Unit Description
Instructional
Hours
I
Introduction to Automata theory
Introduction-Need of automata theory-Formal proof- Additional Forms of
Proof-Inductive Proofs-Central Concepts of Automata Theory-DFA and
NDFA-Finite Automaton with Є- Transitions-Equivalence of DFA and NFA-
Case Study: Finite Automata for Artificial Intelligence, Compilers, Probability
9
II
Regular Expressions
Regular Languages-Regular Expressions-Equivalence of finite Automaton and
regular expressions-Minimization of DFA-Closure Properties and Decision
Properties of Regular Languages-Problems based on Pumping Lemma-
Case Study: Regular Expressions for NLP, Pattern matching, Data extraction
9
III
Context Free Grammars
Chomsky hierarchy of languages-Context-Free Grammar (CFG)-Parse Trees-
Ambiguity in grammars and languages-Normal forms for CFG-Chomsky
Normal Form (CNF)-Greibach Normal Form (GNF)-Pumping Lemma for
Context Free Language (CFL)-Applications of Context Free Grammar. Case
Study:Context Free Grammars in GCC compiler and in XML DTD
9
IV
PushDown Automata and Turing Machines
Definition of the Pushdown automata-Types of PDA-Languages of a
Pushdown Automata - Equivalence of PDA and CFG-Definitions of Turing
machines-Models-Computable languages and functions-Techniques for
Turing machine construction-Multi head and Multi tape Turing Machines.
Turing machines for machine learning and high performance computing
applications
9
V
Undecidability
The Halting problem – Partial Solvability- Undecidability- Decidable and
undecidable problems- Post correspondence problem and Undecidability of
PCP-Basic Definition and properties of Recursive (RL) and Recursively
enumerable (REL) languages. Intractable Problems- the Class P and NP-
Introduction to NP-Hardness and NP-Completeness
9
Total Instructional Hours 45
Course
Outcome
CO1: Understand the theoretical concepts of automata and equivalence of automata
CO2: Remember the automata in applying to obtain regular expressions and languages
CO3: Apply the normalization in context free grammar to obtain optimized CFG
CO4: Understand PDA and turing machines and apply for making mathematical models
CO5: Understand the decidability and tractability problems and apply for developed models

2. HICET – Department of Artificial Intelligence and Machine Learning
TEXT BOOKS:
T1: Hopcroft J.E., Motwani R. and Ullman J.D, “Introduction to Automata Theory, Languages and
Computations”, ThirdEdition, Pearson Education, 2016.
T2: John C Martin, “Introduction to Languages and the Theory of Computation”, Fourth Edition, Tata McGraw
Hill Publishing Company, New Delhi, 2011.
REFERENCE BOOKS:
R1: Mishra K L P and Chandrasekaran N, “Theory of Computer Science - Automata, Languages and
Computation”, Third Edition, Prentice Hall of India, 2016
R2: Harry R Lewis and Christos H Papadimitriou, “Elements of the Theory of Computation”, Second Edition,
Prentice Hall of India, Pearson Education, New Delhi, 2015.
R3: Peter Linz, “An Introduction to Formal Language and Automata”, Sixth Edition, Jones & Bartlett Learning,
2016
CHAIRMAN, BOARD OF STUDIES DEAN-ACADEMICS / PRINCIPAL

3. HICET – Department of Artificial Intelligence and Machine Learning
Programme Course Code Name of the Course L T P C
B. Tech. 19AI6202 Business Intelligence 3 0 0 3
Course
Objective
1. Understand and critically apply the concepts and methods of business analytics.
2. Identify, model and solve decision problems in different settings.
3. Interpret results/solutions and identify appropriate courses of action for a given
managerial situation whether a problem or an opportunity.
4. Create viable solutions to decision making problems.
Unit Description
Instructional
Hours
I
Overview of IBM Cognos BI
Introduction to the reporting application, examine report studio and its interface,
explore, format, group and sort list reports, describe options for aggregating data,
create a report with repeated data.
9
II
Focus Reports using Filters and Create Crosstab Reports
Create filters to narrow the focus of reports, examine detail and summary filters,
determine when to apply filters on aggregate data, format and sort crosstab reports,
convert a list to a crosstab, create crosstabs using unrelated data items and create
complex crosstabs using drag and drop functionality.
9
III
Present Data Graphically and Focus Reports using Prompts
Create charts containing peer and nested items, present data using different chart
type options, add context to charts, Create and reuse custom chart palettes, present
key data in a single dashboard report, identify various prompt types, use parameters
and prompts to focus data, search for prompt items and navigate between pages.
9
IV
Extend Reports using Calculations
Create calculations based on data in the data source, add run-time information to the
reports, create expressions using functions, highlight exceptional data, show and
hide data, conditionally render objects in reports, conditionally format one crosstab
measure.
9
V
Customize Reports with Conditional Formatting
Create multi-lingual reports, highlight exceptional data, create a conditionally
rendered column, conditionally format one crosstab measure based on another.
9
Total Instructional Hours 45
Course
Outcome
CO1: Describe the concepts and components of Business Intelligence (BI).
CO2: Critically evaluate use of BI for supporting decision making in an organization.
CO3: Understand and use the technologies and tools that make up BI (e.g., Data warehousing,
Data reporting and use of Online analytical processing (OLAP)).
CO4: Understand and design the technological architecture that underpins BI systems.
CO5: Plan the implementation of a BI system.
TEXT BOOKS:
T1: IBM CE - Foundation in Business Analytics by IBM CE 2018, Fifth edition (2017).
T2: IBM Cognos Analytics: Author Reports Fundamentals(v11.0) by IBM CE, (2016).

4. HICET – Department of Artificial Intelligence and Machine Learning
REFERENCE BOOKS:
R1: Sangeeta Gautam - IBM Cognos Business Intelligence v10: The Complete Guide (IBM Press) 1st Edition
(2012).
R2: Dustin Adkison - IBM Cognos Business Intelligence (2013).
R3: Dan Volitich and Gerard Ruppert - IBM Cognos Business Intelligence 10: The Official Guide (India)
Private Ltd, 2012
CHAIRMAN, BOARD OF STUDIES DEAN-ACADEMICS / PRINCIPAL

5. HICET – Department of Artificial Intelligence and Machine Learning
Programme Course Code Name of the Course L T P C
B. Tech. 19AI6203 NATURAL LANGUAGE PROCESSING 3 0 0 3
Course
Objective
1. To familiarize the concepts and techniques of Natural language Processing for
analyzing words based on Morphology.
2. Tolerate mathematical foundations, Probability theory with Linguistic essentials such as
syntactic and semantic analysis of text.
3. To apply the Statistical learning methods and cutting-edge research models from deep
learning.
4. To Create CORPUS linguistics based on digestive approach (Text Corpus
method)
5. To check the syntax and semantic used in NLP.
Unit Description
Instructional
Hours
I
INTRODUCTION TO NLP
Introduction to NLP - Various stages of NLP –The Ambiguity of Language:
Why NLP Is Difficult- Parts of Speech: Nouns and Pronouns, Words:
Determiners and adjectives, verbs, Phrase Structure. Statistics Essential
Information Theory : Entropy, perplexity, The relation to language, Cross
entropy
9
II
TEXT PREPROCESSING AND MORPHOLOGY
Character Encoding, Word Segmentation, Sentence Segmentation,
Introduction to Corpora, Corpora Analysis. Inflectional and Derivation
Morphology, Morphological analysis and generation using Finite State
Automata and Finite State transducer.
9
III
LANGUAGE MODELLING
Words: Collocations- Frequency-Mean and Variance –Hypothesis testing: The
t test, Hypothesis testing of differences, Pearson’s chi-square test, Likelihood
ratios. Statistical Inference: n –gram Models over Sparse Data: Bins: Forming
Equivalence Classes- N gram model - Statistical Estimators- Combining
Estimators
9
IV
WORD SENSE DISAMBIGUATION
Methodological Preliminaries, Supervised Disambiguation: Bayesian
classification, An information- theoretic approach, Dictionary-Based
Disambiguation: Disambiguation based on sense, Thesaurus-based
disambiguation, Disambiguation based on translations in a second-language
corpus.
9
V
SYNTAX AND SEMANTICS
Shallow Parsing and Chunking, Shallow Parsing with Conditional Random
Fields (CRF), Lexical Semantics, WordNet, Thematic Roles, Semantic Role
Labelling with CRFs. Statistical Alignment and Machine Translation, Text
alignment, Word alignment, Information extraction, Text mining, Information
Retrieval, NL interfaces, Sentimental Analysis, Question Answering Systems,
Social network analysis.
9
Total Instructional Hours 45
Course
Outcome
CO1: Apply the principles and Process of Human Languages such as English and other Indian
Languages using computers.
CO2: Realize semantics and pragmatics of English language for text processing

6. HICET – Department of Artificial Intelligence and Machine Learning
CO3: Create CORPUS linguistics based on digestive approach (Text Corpus method) and
Check a current methods for statistical approaches to machine translation.
CO4: Develop a Statistical Methods for Real World Applications and explore deep learning
based NLP.
CO5: Demonstrate the state-of-the-art algorithms and techniques for text-based processing of
natural language with respect to morphology.
TEXT BOOKS:
T1: Christopher D. Manning and Hinrich Schutze, “ Foundations of Natural Language Processing” , 6th Edition,
The MIT Press Cambridge, Massachusetts London, England, 2003
T2: Daniel Jurafsky and James H. Martin “Speech and Language Processing”, 3rd edition, Prentice Hall, 2009.
REFERENCE BOOKS:
R1: NitinIndurkhya, Fred J. Damerau “Handbook of Natural Language Processing”, Second Edition, CRC
Press, 2010.
R2: James Allen “Natural Language Understanding”, Pearson Publication 8th Edition. 2012.
R3: Chris Manning and HinrichSchütze, “Foundations of Statistical Natural Language Processing”,2nd
edition, MITPress Cambridge, MA, 2003.
R4: Hobson lane, Cole Howard, Hannes Hapke, “Natural language processing in action”MANNING
Publications, 2019.
R5: Alexander Clark, Chris Fox, Shalom Lappin, “The Handbook of Computational Linguistics and Natural
Language Processing”, Wiley-Blackwell, 2012
R6: Rajesh Arumugam, Rajalingappa Shanmugamani “Hands-on natural language processing with python: A
practical guide to applying deep learning architectures to your NLP application”. PACKT publisher,
2018.
CHAIRMAN, BOARD OF STUDIES DEAN-ACADEMICS / PRINCIPAL

7. HICET – Department of Artificial Intelligence and Machine Learning
Programme Course Code Name of the Course L T P C
B. Tech. 19AI6251 AI Analyst 3 0 2 4
Course
Objective
1. Understand the evolution and relevance of AI in the world today. To read and write simple
Python programs
2. Explore opportunities brought by the intersection between human expertise and machine
learning.
3. Gain a competitive edge using low-code cloud-based AI tools and pre-built machine learning
algorithms
4. Understand AI technology building blocks, including: natural language processing,
machine and deep learning, neural networks, virtual agents, autonomics and computer
vision.
Unit Description
Instructional
Hours
I
AI LANDSCAPE
AI impart in the world today, History and Evolution of AI, AI Explained, AI
Technologies, Summary and Resources.
Illustrative problems: Create IBM Id, setting up your cloud account and apply
promotion code.
6+2
II
AI INDUSTRY ADOPTION APPROACHES
AI Industry Impact, Autonomous Vehicles (CNBC, Autocar, etc.…), Smart
Robotics, Future workforce and AI, Summary and Resources.
Illustrative problems: Analyze, Classify and detect the objects with the help of
Python Code.
8+2
III
NATURAL LANGUAGE UNDERSTANDING
Natural Language Processing Overview, NLP Explained, NLP Program in Python
(NLTK package’s), Virtual Agents Overview, Virtual Agents for the Enterprise,
Summary and Resources.
Illustrative problems: Create an AI virtual assistant with dialog skill using Python.
8+3
IV
COMPUTER VISION
Computer Vision overview, Image processing overview, AI Vision through deep
learning, Computer Vision for the Enterprise, Experiments using Open-CV and
Pillow package, Summary and resources.
Illustrative problems: Classifying Images and apply different filter using open-cv
and pillow package using python.
8+4
V
VI
MACHINE LEARNING AND DEEP LEARNING
Machine Learning Explained, Deep Learning Explained, Deep Learning ecosystem,
Experiments and Implementation with python, Summary and Resources.
Illustrative problems: Implement the regression Algorithm in data set and visualized
the output in scatter chart.
FUTURE TRENDS FOR AI
Artificial intelligence Trends, limits of machine and human, AI predictions in
the 5 years, Summary and Resources.
Illustrative problems: Convert a normal Text to a Speech Format using Python.
8+3
6+2
Total Instructional Hours 44+16

8. HICET – Department of Artificial Intelligence and Machine Learning
Course
Outcome
CO1: Gain a historical perspective of AI and its foundations.
CO2: Become familiar with basic principles of AI toward problem solving, inference,
perception, knowledge representation, and learning.
CO3: Investigate applications of AI techniques in intelligent agents, expert systems, artificial
neural networks and other machine learning models.
CO4: Experiment with a machine learning model for simulation and analysis.
CO5: Explore the current scope, potential, limitations, and implications of intelligent systems
TEXT BOOKS:
T1:
T2:
Tony Boobier - Advanced Analytics and AI, 2018
Artificial Intelligence with Python: A Comprehensive Guide to Building Intelligent Apps for Python
Beginners and Developers Paperback – 27 January 2017
REFERENCE BOOKS:
R1: Artificial Intelligence And Big Data by Fernando Iafrate, Wiley, 2013.
R2: Artificial Intelligence in Intelligent Systems: Proceedings of 10th Computer Science On-line Conference
2021
CHAIRMAN, BOARD OF STUDIES DEAN-ACADEMICS / PRINCIPAL

9. HICET – Department of Artificial Intelligence and Machine Learning
Programme Course Code Name of the Course L T P C
B. Tech. 19AI6001 NATURAL LANGUAGE PROCESSING LAB 0 0 3 1.5
Course
Objective
1. To know about language processing.
2. To create work and know about word generation in NLP.
3. To know about continues language processing.
4. To know the occurrence of word in NLP.
5. To create a programs that is used in NLP for recognizing short phrases.
S. No. Description of the Experiments
1. Word Analysis
2. Word Generation
3. Morphology
4. N-Grams
5. N-Grams Smoothing
6. POS Tagging: Hidden Markov Model
7. POS Tagging: Viterbi Decoding
8. Building POS Tagger
9. Chunking
10. Building Chunker
Total Practical Hours 45
Course
Outcome
Upon completion of this course, the students will be able to
CO1: Understand the basics of NLP
CO2: Design programs for word processing in NLP.
CO3: Develop programs to access continues words in NLP.
CO4: Develop programs to check the how frequently a word appears in NLP.
CO5: Design programs using chunking concepts.
CHAIRMAN, BOARD OF STUDIES DEAN-ACADEMICS / PRINCIPAL